Server Quality Checklist

Tool Scores

• list_sectionsA
  4/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the behavioral burden. 'List' implies a non-mutating operation, and the optional filter is disclosed, but no details are given about matching behavior, ordering, or whether all sections are always returned. The output schema likely covers return structure, but edge-case behavior remains undocumented.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, front-loaded sentence with no filler. It names the resource, the action, and the parameter behavior efficiently.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple list tool with one optional parameter and an output schema, the description covers the essential call semantics. It could be slightly richer by noting substring matching behavior, but nothing critical is missing for a competent agent.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema only shows 'contains' as an optional string/null with no description. The tool description adds meaningful semantics by explaining it as an optional substring filter, which is exactly the missing context. More detail such as case sensitivity would be nice, but for a single optional parameter this is adequate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('List') and resource ('Prothom Alo section slugs'), and clearly mentions the optional substring filter. This distinguishes it from the sibling news-retrieval tools, which operate on articles and search queries rather than section metadata.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The intended use is clear: call this when you need section slugs, optionally narrowed by a substring. However, the description does not explicitly mention when not to use it or name the sibling alternatives, so the usage guidance is implied rather than explicit.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• search_newsA
  4/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description carries the burden of behavioral disclosure. It adds useful behavior context by noting that it works in Bengali or English and that it performs a search rather than a mutation, but it does not disclose details like rate limits, result handling, or pagination.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and front-loaded, with two short sentences and a purpose statement. Every sentence adds value: the first states the operation and resource, the second clarifies language support and intended use.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description is largely complete for a two-parameter search tool: it explains the query, the source, language support, and intended use case. An output schema exists, so return value details are covered. It would be slightly stronger with explicit sibling differentiation or an explanation of the limit parameter.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate. It adds meaning by explaining the query is a keyword search and supports Bengali or English, which clarifies the query parameter. However, the optional limit parameter is not addressed in the description, leaving that meaning solely to the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description names a specific verb and resource: 'Search Prothom Alo articles by keyword.' The use case of tracking a topic, brand, person, or event makes its purpose unmistakable and clearly distinct from siblings like latest_news or list_sections.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly states when to use the tool: for tracking a topic, brand, person, or event in Bangladeshi media. It does not mention when not to use it or name alternatives, but the use case is clear enough to guide selection.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• latest_newsA
  4.5/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description carries the behavioral disclosure burden and does so well: it reveals that the API has no server-side section filter preserving recency, that section requests scan the newest 100 stories, and that quiet sections may return fewer items. It does not mention auth or rate limits, but these are not implied by the tool's simple read/list nature.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and front-loaded, leading with the core behavior, then providing needed parameter guidance and a single caveat. Every sentence adds value and there is no filler or unnecessary repetition of schema fields.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a read-only listing tool with two optional parameters and an output schema, the description covers the core behavior, ordering, section discovery, and the key edge case of local filtering. Nothing necessary for correct invocation is missing.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate. It thoroughly explains `section` with example slugs and points to list_sections for valid values. `limit` is left to the schema, but its meaning is clear from the tool's purpose and default value.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  States a specific verb and resource ('Get the most recent Prothom Alo articles, newest first'), making the tool's function unambiguous. The ordering and scope clearly distinguish it from sibling tools like search_news and read_article.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description offers clear context for the section parameter by instructing the agent to 'Call list_sections to see what exists.' It also explains the local-filtering behavior for sections, though it does not explicitly contrast latest_news with search_news or read_article.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• read_articleA
  4.6/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description carries the responsibility for disclosing safety. The verb 'Read' clearly signals a non-mutating operation, and 'full text' indicates the scope of what will be returned. It does not overpromise details like rate limits or error behavior, but for a straightforward read operation this is adequate.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences with no filler: the first states the tool's primary action and object, and the second defines the accepted input formats. All information is front-loaded and every sentence earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's low complexity (one parameter), the presence of an output schema, and sibling names that make the alternatives obvious, the description is complete. An agent has both the purpose and the exact accepted input format needed to invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Although the schema provides no description for url_or_slug, the tool description fully compensates by explaining that it accepts either a full URL or a bare slug and gives a concrete example. This is exactly the semantic content an agent needs to format the single required parameter correctly.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb and resource: 'Read the full text of one Prothom Alo article.' This clearly distinguishes the tool from siblings like search_news, latest_news, and list_sections: it targets one existing article rather than discovering or listing content.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description states the clear use case: retrieve full text of a specific article, and the input forms (URL or slug) imply you must already have an identifier rather than needing to search. It does not explicitly list exclusions or recommend alternatives, but the context is clear enough to avoid confusion with sibling tools.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.